INDEX

Explanations

references to previous sections or details in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

########.

-0.68

ParallelGroup

-0.65

 المعيارى

-0.64

 <>",

-0.57

findpost

-0.55

Personendaten

-0.54

 propOrder

-0.53

 وتسجيلات

-0.53

 okuyayım

-0.53

makeConstraints

-0.53

POSITIVE LOGITS

sendRedirect

0.61

 elsewhere

0.56

 Xinjiang

0.54

 footnote

0.52

../

0.51

@[+][

0.50

 lighthouse

0.50

 Herod

0.50

paksa

0.49

 deliberation

0.49

Activations Density 0.588%

references to previous sections or details in the text

No Comments

No Known Activations